© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10065
    Prev
    Next
    INDEX
    Explanations

    references to specific data structures, particularly in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.60
    ftagPool
    -0.59
    TextAppearance
    -0.57
    IsMutable
    -0.55
     Meksiku
    -0.54
    ductory
    -0.54
    újo
    -0.54
    wnież
    -0.54
    seteq
    -0.53
    RectangleBorder
    -0.52
    POSITIVE LOGITS
    UserScript
    0.62
    (
    0.58
    WebVitals
    0.58
     Baillargeon
    0.56
     Juifs
    0.55
    (**
    0.54
     sauvages
    0.52
     suffit
    0.52
    ({
    0.52
    ArrowToggle
    0.51
    Activations Density 0.195%

    No Known Activations